Latest Research in Computer Vision and Pattern Recognition
81 research papers · 2026 median publication year
Top Research Topics in Computer Vision and Pattern Recognition
- Computer Vision and Pattern Recognition — 69 papers
- Multimodal Machine Learning Applications — 5 papers
- Video Analysis and Summarization — 2 papers
- Machine Learning — 1 papers
- Artificial Intelligence — 1 papers
- Audio and Speech Processing — 1 papers
- Multimedia — 1 papers
- Computation and Language — 1 papers
Highest-Cited Papers
- Towards Faithful Sentimental Image Captioning via Evidence-Aware Multi-Agent Reasoning
- FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding
- MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing
- Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation
- MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning
- TimePLE: Rethinking Temporal Representation for Video Temporal Grounding
- The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding
- LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos
- A comprehensive survey on feature representation for content based video retrieval
- Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question Answering
- WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
- Temporal modality reliability and uncertainty-aware alignment for text-video retrieval
- WindowQuant: Mixed-Precision KV Cache Quantization Based on Window-Level Similarity for VLMs Inference Optimization
- Cambrian-P: Pose-Grounded Video Understanding
- Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos
- PercepCap: Video Captioner with Structured Spatio-Temporal Perception
- GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models
- PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models
- Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval
- ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning